Back to skill

Security audit

QMD CLI

Security checks across malware telemetry and agentic risk

Overview

This skill appears to provide a local QMD search integration, with install and MCP setup risks that are disclosed and aligned with its purpose.

Install only if you trust the qmd upstream package. Prefer a pinned/released package when possible, review what directories you add as QMD collections, and only run an MCP server or daemon when you intentionally want agents or MCP clients to access that local index.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.